EUVIMEDEUVIMED entdecken
Crossref

Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation

Yachao Zhang, Yuxiang Lan, Yuan Xie, Cuihua Li, Yanyun Qu

IEEE Transactions on Neural Networks and Learning Systems · 2025-08 · 36 (8) · 14452-14463

DOI: 10.1109/tnnls.2025.3526164 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2025-08. Verfasst von Yachao Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 81 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Chongqing, China Computer Federation (CCF) Lenovo Blue Ocean Research Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised point cloud semantic segmentation is an increasingly active topic, because fully supervised learning acquires well-labeled point clouds and entails high costs. The existing weakly supervised methods either need meticulously designed data augmentation for self-supervised learning or ignore the negative effects of learning on pseudolabel noises. In this article, by designing different granularity of cross-cloud structures, we propose a cross-cloud consistency method for weakly supervised point cloud semantic segmentation which forms the expectation-maximum (EM) framework. Benefiting from the cross-cloud constraints, our method allows effective learning alternatively between refining pseudolabels and updating network parameters. Specifically, in E-step, we propose a pseudolabel selecting (PLS) strategy based on cross subcloud consistency, improving the credibility of selected pseudolabels explicitly. In M-step, a cross-scene contrastive regularization enforces cross-scene prototypes with the same label in different scenes to be more similar, while keeping prototypes with different labels to be a clear margin, reducing the noise fitting. Finally, we give some insight into the optimization of our method in the EM theoretical way. The proposed method is evaluated on three challenging datasets, where experimental results demonstrate that our method significantly outperforms state-of-the-art weakly supervised competitors. Our code is available online: https://github.com/Yachao-Zhang/Cross-Cloud-Consistency.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Chongqing
  • China Computer Federation (CCF) Lenovo Blue Ocean Research Fund
  • China Academy of Railway Sciences

Zitieren

APA

Zhang, Y., Lan, Y., Xie, Y., Li, C., & Qu, Y. (2025). Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems, 36(8), 14452-14463. https://doi.org/10.1109/tnnls.2025.3526164

Vancouver

Zhang Y, Lan Y, Xie Y, Li C, Qu Y. Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems. 2025;36(8):14452-14463. doi:10.1109/tnnls.2025.3526164

BibTeX
@article{Zhang2025,
  author = {Zhang, Yachao and Lan, Yuxiang and Xie, Yuan and Li, Cuihua and Qu, Yanyun},
  title = {Cross-Cloud Consistency for Weakly Supervised Point Cloud Semantic Segmentation},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2025},
  volume = {36},
  number = {8},
  pages = {14452--14463},
  doi = {10.1109/tnnls.2025.3526164}
}
Kostenlos starten →